ClawHub
Back to skill

Security audit

Google Keep

Security checks across malware telemetry and agentic risk

Overview

This Google Keep skill does what it says, but it can access and modify your notes and stores a reusable local token.

Install only if you are comfortable giving this tool access to your Google Keep notes. Use a Google App Password rather than your regular password, review note IDs before running mutation commands, and remove ~/.config/gkeep/token.json or revoke the app password if you no longer want the skill to have access.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill documents and requires capabilities such as shell execution and file read/write, including local venv bootstrap and token storage, but does not declare permissions. This creates a transparency and policy gap: users or orchestrators may authorize or run the skill without understanding that it can access the filesystem, environment, and execute commands.

Missing User Warnings

Low
Confidence
80% confidence
Finding
The skill exposes archive and delete operations on user notes without any caution about data modification or loss. While these commands are expected for a note-management tool, omission of warnings or confirmation guidance increases the chance of accidental destructive actions against personal data.

Unpinned Dependencies

Low
Category
Supply Chain
Content
gkeepapi>=0.14.0
Confidence
91% confidence
Finding
gkeepapi>=0.14.0

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.